X-ReID: Cross-Instance Transformer for Identity-Level Person Re-Identification

TL;DR

This paper introduces X-ReID, a novel transformer-based framework that enhances person re-identification by leveraging cross-instance attention to unify and discriminate identity features across images.

Contribution

The paper proposes a new training framework with cross-attention modules that transfer identity-level knowledge and improve feature discrimination in person re-identification.

Findings

Achieves 1.1% mAP improvement on MSMT17 dataset.

Outperforms existing methods on benchmark datasets.

Effectively reduces intra-identity variation and increases inter-identity distinction.

Abstract

Currently, most existing person re-identification methods use Instance-Level features, which are extracted only from a single image. However, these Instance-Level features can easily ignore the discriminative information due to the appearance of each identity varies greatly in different images. Thus, it is necessary to exploit Identity-Level features, which can be shared across different images of each identity. In this paper, we propose to promote Instance-Level features to Identity-Level features by employing cross-attention to incorporate information from one image to another of the same identity, thus more unified and discriminative pedestrian information can be obtained. We propose a novel training framework named X-ReID. Specifically, a Cross Intra-Identity Instances module (IntraX) fuses different intra-identity instances to transfer Identity-Level knowledge and make Instance-Level features more compact. A Cross Inter-Identity Instances module (InterX) involves hard positive and hard negative instances to improve the attention response to the same identity instead of different identity, which minimizes intra-identity variation and maximizes inter-identity variation. Extensive experiments on benchmark datasets show the superiority of our method over existing works. Particularly, on the challenging MSMT17, our proposed method gains 1.1% mAP improvements when compared to the second place.